© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206871
    Prev
    Next
    INDEX
    Explanations

    toothpaste

    np_acts-logits-general · gemini-2.5-flash-lite

    questions and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cornwall
    0.53
     disclaimer
    0.50
     locale
    0.49
    -
    0.49
    s
    0.48
     restrictive
    0.47
    _
    0.47
    0.47
    悟
    0.46
     Dorset
    0.46
    POSITIVE LOGITS
     डाई
    0.58
     )।
    0.55
     فنا
    0.54
    堞
    0.54
     對
    0.53
     브랜드
    0.52
    𝗙
    0.51
    toothpaste
    0.50
     фара
    0.50
    ﾁ
    0.49
    Activations Density 0.000%

    No Known Activations